Track topics on Twitter Track topics that are important to you
In many data classification problems, a number of methods will give similar accuracy. However, when working with people who are not experts in data science such as doctors, lawyers, and judges among others, finding interpretable algorithms can be a critical success factor. Practitioners have a deep understanding of the individual input variables but far less insight into how they interact with each other. For example, there may be ranges of an input variable for which the observed outcome is significantly more or less likely. This paper describes an algorithm for automatic detection of such thresholds, called the Univariate Flagging Algorithm (UFA). The algorithm searches for a separation that optimizes the difference between separated areas while obtaining a high level of support. We evaluate its performance using six sample datasets and demonstrate that thresholds identified by the algorithm align well with published results and known physiological boundaries. We also introduce two classification approaches that use UFA and show that the performance attained on unseen test data is comparable to or better than traditional classifiers when confidence intervals are considered. We identify conditions under which UFA performs well, including applications with large amounts of missing or noisy data, applications with a large number of inputs relative to observations, and applications where incidence of the target is low. We argue that ease of explanation of the results, robustness to missing data and noise, and detection of low incidence adverse outcomes are desirable features for clinical applications that can be achieved with relatively simple classifier, like UFA.
This article was published in the following journal.
Name: PloS one
We developed an algorithm for identifying U.S. veterans with a history of posttraumatic stress disorder (PTSD), using the Department of Veterans Affairs (VA) electronic medical record (EMR) system. Th...
Resting-state and task-based functional connectivity matrices, or connectomes, are powerful predictors of individual differences in phenotypic measures. However, most of the current state-of-the-art a...
Phenotypic heritability of complex traits and diseases is seldom explained by individual genetic variants identified in genome-wide association studies (GWAS). Many methods have been developed to sele...
An unambiguous algorithm, added to the study of the applicability domain and appropriate measures of the goodness of fit and robustness, represent the key characteristics that should be ideally fulfil...
The chapter is focused on methods relevant for predictive toxicology and computer-aided drug design (adverse outcome pathway development, pharmacophore modeling, docking, and 3D QSAR analysis) and app...
The purpose of this study was to investigate the risk factors for mortality of sepsis and to create mathematical models to predict the survival rate based on electronic health records that...
In this prospective study, the ability of a machine learning algorithm to predict sepsis and influence clinical outcomes, will be investigated at Cabell Huntington Hospital (CHH).
The purpose of the current study is to determine if pre-exposure through video modeling will enhance testing compliance in a population of children who are receiving a diagnostic evaluatio...
The objective of this randomized crossover clinical trial is to 1) assess the efficacy and safety of an automated insulin delivery (AID) system using a Model Predictive Control (MPC) algor...
The investigators are studying the duration it takes surgeons to complete their respective surgical cases. The hospital hopes to improve the overall operating room scheduling accuracy from...
In screening and diagnostic tests, the probability that a person with a positive test is a true positive (i.e., has the disease), is referred to as the predictive value of a positive test; whereas, the predictive value of a negative test is the probability that the person with a negative test does not have the disease. Predictive value is related to the sensitivity and specificity of the test.
A statistical tool for detecting and modeling gene-gene interactions. It is a non-parametric and model-free approach.
Any situation where an animal or human is trained to respond differentially to two stimuli (e.g., approach and avoidance) under reward and punishment conditions and subsequently trained under reversed reward values (i.e., the approach which was previously rewarded is punished and vice versa).
A nondirective psychotherapy approach originated by Carl Rogers. The goals of therapy are to promote the client’s congruence, self awareness, and self acceptance. This approach views the client as naturally directed toward self actualization, and only needing facilitative conditions in order to promote this tendency.
Brief therapeutic approach which is ameliorative rather than curative of acute psychiatric emergencies. Used in contexts such as emergency rooms of psychiatric or general hospitals, or in the home or place of crisis occurrence, this treatment approach focuses on interpersonal and intrapsychic factors and environmental modification. (APA Thesaurus of Psychological Index Terms, 7th ed)